Long Range Graph Benchmark
Long Range Graph Benchmark
复制标题
DOI：
10.48550/arxiv.2206.08164
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Vijay Prakash Dwivedi;Ladislav Rampášek;Mikhail Galkin;Alipanah Parviz;Guy Wolf;A. Luu;D. Beaini
中科院分区：
文献类型：
--
作者：
Vijay Prakash Dwivedi;Ladislav Rampášek;Mikhail Galkin;Alipanah Parviz;Guy Wolf;A. Luu;D. Beaini
基于消息传递（MP）范式的图形神经网络（GNN）通常在1-HOP邻居之间交换信息，以在每一层构建节点表示。原则上，此类网络无法捕获在图形上学习给定任务的可能或必需的远程交互（LRI）。最近，人们对基于变压器的方法的开发越来越兴趣，这些方法可以考虑超出原始稀疏结构以外的完整节点连接，从而实现了LRI的建模。但是，与位置特征表示形式结合使用时，简单地依靠1跳消息传递的MP-gnn通常在几个现有的图形基准中表现更好，因此，限制了变形金刚样体系结构的感知效用和排名。在这里，我们介绍了5个图形学习数据集的远程图基准（LRGB）：Pascalvoc-SP，Coco-SP，PCQM-Contact，Peptides-Func和肽结构，可以说需要LRI推理才能在给定任务中实现强大的性能。我们基准测试基线GNN和Graph Transformer网络，以验证捕获长期依赖性的模型在这些任务上的性能明显更好。因此，这些数据集适用于旨在捕获LRI的MP-GNN和Graph Transformer架构的基准测试和探索。
Graph Neural Networks (GNNs) that are based on the message passing (MP) paradigm generally exchange information between 1-hop neighbors to build node representations at each layer. In principle, such networks are not able to capture long-range interactions (LRI) that may be desired or necessary for learning a given task on graphs. Recently, there has been an increasing interest in development of Transformer-based methods for graphs that can consider full node connectivity beyond the original sparse structure, thus enabling the modeling of LRI. However, MP-GNNs that simply rely on 1-hop message passing often fare better in several existing graph benchmarks when combined with positional feature representations, among other innovations, hence limiting the perceived utility and ranking of Transformer-like architectures. Here, we present the Long Range Graph Benchmark (LRGB) with 5 graph learning datasets: PascalVOC-SP, COCO-SP, PCQM-Contact, Peptides-func and Peptides-struct that arguably require LRI reasoning to achieve strong performance in a given task. We benchmark both baseline GNNs and Graph Transformer networks to verify that the models which capture long-range dependencies perform significantly better on these tasks. Therefore, these datasets are suitable for benchmarking and exploration of MP-GNNs and Graph Transformer architectures that are intended to capture LRI.